Presentation 2002/4/19
In-Car Speech Recognition based on Multiple Regression of Spectra
Tetsuya SINDE, Kazuya TAKEDA, Fumitada ITAKURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a new multichannel method of noisy speech recognition, which estimates the log spectrum of speech at a close-talking microphone based on the multiple regression of the log spectra (MRLS) of noisy signals captured by the distributed microphones. Since the method does not assume the arrangement of sound sources and microphones, it can be applied to in-car speech recognition directly. The experimental evaluation shows an error reduction of up to 15% in isolated word recognition accuracy under various driving conditions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) in-car speech recognition / noise-robust / multiple regression analysis / multiple microphone
Paper # EA2002-10
Date of Issue

Conference Information
Committee EA
Conference Date 2002/4/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Engineering Acoustics (EA)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) In-Car Speech Recognition based on Multiple Regression of Spectra
Sub Title (in English)
Keyword(1) in-car speech recognition
Keyword(2) noise-robust
Keyword(3) multiple regression analysis
Keyword(4) multiple microphone
1st Author's Name Tetsuya SINDE
1st Author's Affiliation Graduate School of Engineering, Nagoya University()
2nd Author's Name Kazuya TAKEDA
2nd Author's Affiliation Graduate School of Engineering, Nagoya University
3rd Author's Name Fumitada ITAKURA
3rd Author's Affiliation Graduate School of Engineering, Nagoya University
Date 2002/4/19
Paper # EA2002-10
Volume (vol) vol.102
Number (no) 33
Page pp.pp.-
#Pages 4
Date of Issue